23990
Admin: @Raminmousa1 ID: @Machine_learn link: https://t.me/Machine_learn
LMM-R1: Empowering 3B LMMs with Strong Reasoning Abilities Through Two-Stage Rule-Based RL
10 Mar 2025 · Yingzhe Peng, Gongrui Zhang, Miaosen Zhang, Zhiyuan You, Jie Liu, Qipeng Zhu, Kai Yang, Xingzhong Xu, Xin Geng, Xu Yang
Enhancing reasoning in Large Multimodal Models (#LMMs) faces unique challenges from the complex interplay between visual perception and logical reasoning, particularly in compact 3B-parameter architectures where architectural constraints limit reasoning capacity and modality alignment. While rule-based reinforcement learning (RL) excels in text-only domains, its multimodal extension confronts two critical barriers: (1) data limitations due to ambiguous answers and scarce complex reasoning examples, and (2) degraded foundational reasoning induced by multimodal pretraining. To address these challenges, we propose \textbf{\method}, a two-stage framework adapting rule-based RL for multimodal reasoning through \textbf{Foundational Reasoning Enhancement (FRE)} followed by \textbf{Multimodal Generalization Training (MGT)}. The FRE stage first strengthens reasoning abilities using text-only data with rule-based RL, then the MGT stage generalizes these reasoning capabilities to multimodal domains. Experiments on Qwen2.5-VL-Instruct-3B demonstrate that \method achieves 4.83\% and 4.5\% average improvements over baselines in multimodal and text-only benchmarks, respectively, with a 3.63\% gain in complex Football Game tasks. These results validate that text-based reasoning enhancement enables effective multimodal generalization, offering a data-efficient paradigm that bypasses costly high-quality multimodal training data.
Paper: https://arxiv.org/pdf/2503.07536v1.pdf
code: https://github.com/tidedra/lmm-r1
@Machine_learn
با عرض سلام براي مقاله بالا نياز به co-author (نفر اول) هستيم.
مجله پيشنهادي جهت سابميت.
https://www.springerprofessional.de/financial-innovation/50101254
If6️⃣. 5
🔺🔺🔺🔸🔸🔸🔺🔺🔺
جهت ثبت اسم با ايدي بنده در ارتباط باشين
@Raminmousa
@Machine_learn
@paper4money
Seg-Zero: Reasoning-Chain Guided Segmentation via Cognitive Reinforcement
🖥 Github: https://github.com/yunncheng/MMRL
📕 Paper: https://arxiv.org/abs/2503.08497v1
🌟 Dataset: https://paperswithcode.com/dataset/imagenet-s
@Machine_learn
📽 Genomics in Cancer Care
🎞 Watch
@Machine_learn
با عرض سلام براي مقاله بالا نياز به نفر سوم ام هستيم.
مجله پيشنهادي جهت سابميت.
https://www.springerprofessional.de/financial-innovation/50101254
If6️⃣. 5
هزینه نفر سوم ۱۵ میلیون می باشد
🔺🔺🔺🔸🔸🔸🔺🔺🔺
جهت ثبت اسم با ايدي بنده در ارتباط باشين
@Raminmousa
@Machine_learn
@paper4money
The Matrix Cookbook
📚 Link
@Machine_learn
🔥 Exercises in Machine Learning
Book
@Machine_learn
باعرض سلام امشب اخرین فرصت برای مشارکت در این مقاله می باشد.
@Raminmousa
با عرض سلام براي مقاله بالا نياز به نفر 1 یا سوم ام هستيم.
مجله پيشنهادي جهت سابميت.
https://www.springerprofessional.de/financial-innovation/50101254
If6️⃣. 5
هزینه نفر اول ۵۰۰$ و هزینه نفر سوم ۳۰۰$ می باشد
🔺🔺🔺🔸🔸🔸🔺🔺🔺
جهت ثبت اسم با ايدي بنده در ارتباط باشين
@Raminmousa
@Machine_learn
@paper4money
Kiss3DGen: Repurposing Image Diffusion Models for 3D Asset Generation
🖥 Github: https://github.com/EnVision-Research/Kiss3DGen
📕 Paper: https://arxiv.org/abs/2503.01370v1
🌟 Dataset: https://paperswithcode.com/dataset/nerf
@Machine_learn
CS229 Lecture Notes
Andrew Ng and Tengyu Ma
📚 Link
@Machine_learn
📄The role and application of bioinformatics techniques and tools in drug discovery
📎 Study the paper
@Machine_learn
DeepSeek-V3/R1 Inference System Overview
📚 Read
@Machine_learn
با عرض سلام نفر سوم از مقاله زير را نياز داريم.
Title: Wavelet transform and deep average model for price and illiquidity prediction cryptocurrencies using high-dimensional features
🔸🔸🔸🔸🔸🔸🔸🔸
abstarct: Cryptocurrencies are alternative payment methods that are created using encrypted algorithms. Encryption technologies mean that cryptocurrencies act as both a currency and a virtual accounting system. The global crypto market value is \$2.9 trillion. Hence, it requires high investment requirements. One of the challenging issues in cryptocurrencies is illiquidity. Due to behavioural chaos in the market, some currencies have severe dumps and pumps, which cause concerns for investors. This paper deals with price prediction and illiquidity prediction (converting one asset to another while maintaining its value). The proposed Wavelet Deep average model uses a combination of Wavelet transform and average deep learning models for the final prediction. This model uses the hash rate information of currencies as the main inputs. Then, it achieves the selection of a subset of features using a Random Forest(RF). The selected features are designed by a Wavelet and are considered as the input to the deep network. Four currencies, BTC, Dogecoin, Ethereum(ETH), and Bitcoin Cash(BCH), were considered for model evaluation. In Bitcoin prediction, the lowest MAE for price prediction and illiquidity was achieved, which was 1.19 and 1.49, respectively. Also, the proposed model achieved MAE of 1.99, 3.69, and 2.99 for the illiquidity of three currencies Dogecoin, ETH, and BCH. The implementation codes are available in https://github.com/Ramin1Mousa/.
Journal:
Neural computing and application (springer)
@Raminmousa
Hawk: Learning to Understand Open-World Video Anomalies
27 May 2024 · Jiaqi Tang, Hao Lu, Ruizheng Wu, Xiaogang Xu, Ke Ma, Cheng Fang, Bin Guo, Jiangbo Lu, Qifeng Chen, Ying-Cong Chen ·
Video Anomaly Detection (#VAD) systems can autonomously monitor and identify disturbances, reducing the need for manual labor and associated costs. However, current VAD systems are often limited by their superficial semantic understanding of scenes and minimal user interaction. Additionally, the prevalent data scarcity in existing datasets restricts their applicability in open-world scenarios. In this paper, we introduce Hawk, a novel framework that leverages interactive large Visual Language Models (#VLM) to interpret video anomalies precisely. Recognizing the difference in motion information between abnormal and normal videos, Hawk explicitly integrates motion modality to enhance anomaly identification. To reinforce motion attention, we construct an auxiliary consistency loss within the motion and video space, guiding the video branch to focus on the motion modality. Moreover, to improve the interpretation of motion-to-language, we establish a clear supervisory relationship between motion and its linguistic representation. Furthermore, we have annotated over 8,000 anomaly videos with language descriptions, enabling effective training across diverse open-world scenarios, and also created 8,000 question-answering pairs for users' open-world questions. The final results demonstrate that #Hawk achieves SOTA performance, surpassing existing baselines in both video description generation and question-answering. Our codes/dataset/demo will be released at https://github.com/jqtangust/hawk.
Paper: https://arxiv.org/pdf/2405.16886v1.pdf
Code: https://github.com/jqtangust/hawk
Dataset: Hawk Annotation Dataset
@Machine_learn
This channels is for Programmers, Coders, Software Engineers.
0️⃣ Python
1️⃣ Data Science
2️⃣ Machine Learning
3️⃣ Data Visualization
4️⃣ Artificial Intelligence
5️⃣ Data Analysis
6️⃣ Statistics
7️⃣ Deep Learning
8️⃣ programming Languages
✅ /channel/addlist/8_rRW2scgfRhOTc0
✅ /channel/codeprogrammer
VideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control
7 Mar 2025 · Yuxuan Bian, Zhaoyang Zhang, Xuan Ju, Mingdeng Cao, Liangbin Xie, Ying Shan, Qiang Xu ·
Video inpainting, which aims to restore corrupted video content, has experienced substantial progress. Despite these advances, existing methods, whether propagating unmasked region pixels through optical flow and receptive field priors, or extending image-inpainting models temporally, face challenges in generating fully masked objects or balancing the competing objectives of background context preservation and foreground generation in one model, respectively. To address these limitations, we propose a novel dual-stream paradigm VideoPainter that incorporates an efficient context encoder (comprising only 6% of the backbone parameters) to process masked videos and inject backbone-aware background contextual cues to any pre-trained video DiT, producing semantically consistent content in a plug-and-play manner. This architectural separation significantly reduces the model's learning complexity while enabling nuanced integration of crucial background context. We also introduce a novel target region ID resampling technique that enables any-length video inpainting, greatly enhancing our practical applicability. Additionally, we establish a scalable dataset pipeline leveraging current vision understanding models, contributing VPData and VPBench to facilitate segmentation-based inpainting training and assessment, the largest video inpainting dataset and benchmark to date with over 390K diverse clips. Using inpainting as a pipeline basis, we also explore downstream applications including video editing and video editing pair data generation, demonstrating competitive performance and significant practical potential. Extensive experiments demonstrate VideoPainter's superior performance in both any-length video inpainting and editing, across eight key metrics, including video quality, mask region preservation, and textual coherence.
Paper: https://arxiv.org/pdf/2503.05639v2.pdf
Code: https://github.com/TencentARC/VideoPainter
Datasets: VPData - VPBench
@Machine_learn
MonSter: Marry Monodepth to Stereo Unleashes Power
15 Jan 2025 · Junda Cheng, Longliang Liu, Gangwei Xu, Xianqi Wang, Zhaoxing Zhang, Yong Deng, Jinliang Zang, Yurui Chen, Zhipeng Cai, Xin Yang ·
Stereo matching recovers depth from image correspondences. Existing methods struggle to handle ill-posed regions with limited matching cues, such as occlusions and textureless areas. To address this, we propose MonSter, a novel method that leverages the complementary strengths of monocular depth estimation and stereo matching. MonSter integrates monocular depth and stereo matching into a dual-branch architecture to iteratively improve each other. Confidence-based guidance adaptively selects reliable stereo cues for monodepth scale-shift recovery. The refined monodepth is in turn guides stereo effectively at ill-posed regions. Such iterative mutual enhancement enables MonSter to evolve monodepth priors from coarse object-level structures to pixel-level geometry, fully unlocking the potential of stereo matching. As shown in Fig.1, MonSter ranks 1st across five most commonly used leaderboards -- SceneFlow, KITTI 2012, KITTI 2015, Middlebury, and ETH3D. Achieving up to 49.5% improvements (Bad 1.0 on ETH3D) over the previous best method. Comprehensive analysis verifies the effectiveness of MonSter in ill-posed regions. In terms of zero-shot generalization, MonSter significantly and consistently outperforms state-of-the-art across the board. The code is publicly available at: https://github.com/Junda24/MonSter.
Paper: https://arxiv.org/pdf/2501.08643v1.pdf
Code: https://github.com/junda24/monster
Datasets: KITTI - TartanAir
@Machine_learn
Everything You Always Wanted To Know About Mathematics*
📓 book
@Machine_learn
Controlling Latent Diffusion Using Latent CLIP
📚 Read
@Machine_learn
با عرض سلام برای مقاله زیر نیاز به کسی داریم که هزینه سرور با ما شریک بشه.
Multi-modal wound classification using wound image and location by vit-wavelet and transformer
🔸🔸🔸🔸🔸🔸🔸
Jouranl: scientific reports(nature)
هزینه مشارکت نفر ۵ ام ۳۰۰$ می باشد.
🔻@Raminmousa
A SURVEY ON POST-TRAINING OF LARGE LANGUAGE MODELS
📚 Read
@Machine_learn
Attention from Beginners Point of View
📚 Reed
@Machine_learn
Know You First and Be You Better: Modeling Human-Like User Simulators via Implicit Profiles
26 Feb 2025 · Kuang Wang, Xianfei Li, Shenghao Yang, Li Zhou, Feng Jiang, Haizhou Li ·
User simulators are crucial for replicating human interactions with dialogue systems, supporting both collaborative training and automatic evaluation, especially for large language models (LLMs). However, existing simulators often rely solely on text utterances, missing implicit user traits such as personality, speaking style, and goals. In contrast, persona-based methods lack generalizability, as they depend on predefined profiles of famous individuals or archetypes. To address these challenges, we propose User Simulator with implicit Profiles (#USP), a framework that infers implicit user profiles from human-machine conversations and uses them to generate more personalized and realistic dialogues. We first develop an LLM-driven extractor with a comprehensive profile schema. Then, we refine the simulation through conditional supervised fine-tuning and reinforcement learning with cycle consistency, optimizing it at both the utterance and conversation levels. Finally, we adopt a diverse profile sampler to capture the distribution of real-world user profiles. Experimental results demonstrate that USP outperforms strong baselines in terms of authenticity and diversity while achieving comparable performance in consistency. Furthermore, dynamic multi-turn evaluations based on USP strongly align with mainstream benchmarks, demonstrating its effectiveness in real-world applications
.
Paper: https://arxiv.org/pdf/2502.18968v1.pdf
Code: https://github.com/wangkevin02/USP
Dataset: LMSYS-USP
@Machine_learn
با عرض سلام براي مقاله بالا نياز به نفر ٣ ام هستيم.
مجله هاي پيشنهادي جهت سابميت.
🔺🔺🔺🔸🔸🔸🔺🔺🔺
-Soft computing
- Computational Economics
- Multimedia Tools and Applicaion
جهت ثبت اسم با ايدي بنده در ارتباط باشين
@Raminmousa
@Machine_learn
@paper4money
ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents
25 Feb 2025 · Qiuchen Wang, Ruixue Ding, Zehui Chen, Weiqi Wu, Shihang Wang, Pengjun Xie, Feng Zhao ·
Understanding information from visually rich documents remains a significant challenge for traditional Retrieval-Augmented Generation (RAG) methods. Existing benchmarks predominantly focus on image-based question answering (QA), overlooking the fundamental challenges of efficient retrieval, comprehension, and reasoning within dense visual documents. To bridge this gap, we introduce ViDoSeek, a novel dataset designed to evaluate RAG performance on visually rich documents requiring complex reasoning. Based on it, we identify key limitations in current RAG approaches: (i) purely visual retrieval methods struggle to effectively integrate both textual and visual features, and (ii) previous approaches often allocate insufficient reasoning tokens, limiting their effectiveness. To address these challenges, we propose #ViDoRAG, a novel multi-agent RAG framework tailored for complex reasoning across visual documents. ViDoRAG employs a Gaussian Mixture Model (GMM)-based hybrid strategy to effectively handle multi-modal retrieval. To further elicit the model's reasoning capabilities, we introduce an iterative agent workflow incorporating exploration, summarization, and reflection, providing a framework for investigating test-time scaling in RAG domains. Extensive experiments on ViDoSeek validate the effectiveness and generalization of our approach. Notably, ViDoRAG outperforms existing methods by over 10% on the competitive #ViDoSeek benchmark.
Paper: https://arxiv.org/pdf/2502.18017v1.pdf
Code: https://github.com/Alibaba-NLP/ViDoRAG
@Machine_learn
با عرض سلام این مقاله امشب فرایند سابمیتش دوستانی که نیاز به مشارکت دارن می تونن شرکت کنند.
@Raminmousa
people : Ai is so smart
AI :
@Machine_learn
📃 A review on federated learning in computational pathology
📎 Study the paper
@Machine_learn
با عرض سلام برای یکی از کارهای سریزمانی با استفاده از Whighted Deep Neural Network و Wavelet نیاز به نویسنده مسول داریم.
نفر ۴ ام از مقاله خواهند بود. هزینه این مشارکت 250 دلار و دوستانی که نیاز دارند جهت بررسی جزئیات بیشتر به ایدی بنده پیام بدن.
@Raminmousa